azure-mgmt-botservice-py
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Untrusted Data Ingestion: The skill accepts user-provided inputs—such as resource names, display names, and endpoint URLs—which are then passed to Azure management APIs. This creates a surface for indirect prompt injection where malicious content within the data could attempt to alter the agent's execution flow.
- Ingestion points: Bot creation and update functions in
SKILL.mdandnon-hero-scenarios.md. - Capability inventory: Full CRUD operations on Azure Bot Service and channel configurations via
azure-mgmt-botservice. - Boundary markers: The skill does not currently define explicit boundary markers or "ignore instructions" warnings for processed data.
- Sanitization: No explicit sanitization or validation of input strings is demonstrated in the code snippets.
- Sensitive Information Retrieval: The skill includes functionality to retrieve and display Direct Line channel keys (
list_with_keys). While necessary for certain management tasks, displaying these keys in the agent's output context is a security consideration that warrants careful handling to avoid accidental exposure in logs or session history.
Audit Metadata